annotate lisp/soundex.el @ 19860:c17fd465ea95 libc-970911 libc-970912 libc-970913 libc-970914 libc-970915 libc-970916 libc-970917 libc-970918 libc-970919 libc-970920 libc-970921 libc-970922 libc-970923 libc-970924 libc-970925 libc-970926 libc-970927 libc-970928 libc-970929 libc-970930 libc-971001 libc-971018 libc-971019 libc-971020 libc-971021 libc-971022 libc-971023 libc-971024 libc-971025 libc-971026 libc-971027 libc-971028 libc-971029 libc-971030 libc-971031 libc-971101 libc-971102 libc-971103 libc-971104 libc-971105 libc-971106 libc-971107 libc-971108 libc-971109 libc-971110 libc-971111 libc-971112 libc-971113 libc-971114 libc-971115 libc-971116 libc-971117 libc-971118 libc-971120 libc-971121 libc-971122 libc-971123 libc-971124 libc-971125 libc-971126 libc-971127 libc-971128 libc-971129 libc-971130 libc-971201 libc-971203 libc-971204 libc-971205 libc-971206 libc-971207 libc-971208 libc-971209 libc-971210 libc-971211 libc-971212 libc-971213 libc-971214 libc-971217 libc-971218 libc-971219 libc-971220 libc-971221 libc-971222 libc-971223 libc-971224 libc-971225 libc-971226 libc-971227 libc-971228 libc-971229 libc-971230 libc-971231 libc-980103 libc-980104 libc-980105 libc-980106 libc-980107 libc-980108 libc-980109 libc-980110 libc-980111 libc-980112 libc-980114 libc-980115 libc-980116 libc-980117 libc-980118 libc-980119 libc-980120 libc-980121 libc-980122 libc-980123 libc-980124 libc-980125 libc-980126 libc-980127 libc-980128

typos.
author Jeff Law <law@redhat.com>
date Wed, 10 Sep 1997 21:16:20 +0000
parents 11218164bc54
children 253f761ad37b
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
15261
bd56cdc4d07b Fixed up initial line
Erik Naggum <erik@naggum.no>
parents: 14169
diff changeset
1 ;;; soundex.el --- implement Soundex algorithm
5995
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
2
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
3 ;; Copyright (C) 1993 Free Software Foundation, Inc.
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
4
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
5 ;; Author: Christian Plaunt <chris@bliss.berkeley.edu>
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
6 ;; Maintainer: FSF
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
7 ;; Keywords: matching
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
8 ;; Created: Sat May 15 14:48:18 1993
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
9
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
10 ;; This file is part of GNU Emacs.
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
11
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
12 ;; GNU Emacs is free software; you can redistribute it and/or modify
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
13 ;; it under the terms of the GNU General Public License as published by
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
14 ;; the Free Software Foundation; either version 2, or (at your option)
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
15 ;; any later version.
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
16
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
17 ;; GNU Emacs is distributed in the hope that it will be useful,
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
18 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
19 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
20 ;; GNU General Public License for more details.
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
21
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
22 ;; You should have received a copy of the GNU General Public License
14169
83f275dcd93a Update FSF's address.
Erik Naggum <erik@naggum.no>
parents: 8028
diff changeset
23 ;; along with GNU Emacs; see the file COPYING. If not, write to the
83f275dcd93a Update FSF's address.
Erik Naggum <erik@naggum.no>
parents: 8028
diff changeset
24 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
83f275dcd93a Update FSF's address.
Erik Naggum <erik@naggum.no>
parents: 8028
diff changeset
25 ;; Boston, MA 02111-1307, USA.
5995
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
26
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
27 ;;; Commentary:
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
28
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
29 ;; The Soundex algorithm maps English words into representations of
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
30 ;; how they sound. Words with vaguely similar sound map to the same string.
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
31
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
32 ;;; Code:
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
33
7534
9b82dae27c01 (soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents: 5995
diff changeset
34 (defvar soundex-alist
8028
ba1bbdb8595e (soundex-alist): Delete the elements that mapped into nil.
Richard M. Stallman <rms@gnu.org>
parents: 7534
diff changeset
35 '((?B . "1") (?F . "1") (?P . "1") (?V . "1")
7534
9b82dae27c01 (soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents: 5995
diff changeset
36 (?C . "2") (?G . "2") (?J . "2") (?K . "2") (?Q . "2") (?S . "2")
9b82dae27c01 (soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents: 5995
diff changeset
37 (?X . "2") (?Z . "2") (?D . "3") (?T . "3") (?L . "4") (?M . "5")
9b82dae27c01 (soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents: 5995
diff changeset
38 (?N . "5") (?R . "6"))
9b82dae27c01 (soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents: 5995
diff changeset
39 "Alist of chars-to-key-code for building Soundex keys.")
9b82dae27c01 (soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents: 5995
diff changeset
40
5995
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
41 (defun soundex (word)
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
42 "Return a Soundex key for WORD.
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
43 Implemented as described in:
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
44 Knuth, Donald E. \"The Art of Computer Programming, Vol. 3: Sorting
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
45 and Searching\", Addison-Wesley (1973), pp. 391-392."
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
46 (let* ((word (upcase word)) (length (length word))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
47 (code (cdr (assq (aref word 0) soundex-alist)))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
48 (key (substring word 0 1)) (index 1) (prev-code code))
8028
ba1bbdb8595e (soundex-alist): Delete the elements that mapped into nil.
Richard M. Stallman <rms@gnu.org>
parents: 7534
diff changeset
49 ;; once we have a four char key, we're done
5995
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
50 (while (and (> 4 (length key)) (< index length))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
51 ;; look up the code for each letter in word at index
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
52 (setq code (cdr (assq (aref word index) soundex-alist))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
53 index (1+ index)
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
54 ;; append code to key unless the same codes belong to
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
55 ;; adjacent letters in the original string
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
56 key (concat key (if (or (null code) (string= code prev-code))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
57 ()
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
58 code))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
59 prev-code code))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
60 ;; return a key that is 4 chars long and padded by "0"s if needed
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
61 (if (> 4 (length key))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
62 (substring (concat key "000") 0 4)
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
63 key)))
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
64
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
65 ;(defvar soundex-test
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
66 ; '("Euler" "Gauss" "Hilbert" "Knuth" "Lloyd" "Lukasiewicz"
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
67 ; "Ellery" "Ghosh" "Heilbronn" "Kant" "Ladd" "Lissajous")
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
68 ; "\n Knuth's names to demonstrate the Soundex algorithm.")
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
69 ;
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
70 ;(mapcar 'soundex soundex-test)
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
71 ;("E460" "G200" "H416" "K530" "L300" "L222"
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
72 ; "E460" "G200" "H416" "K530" "L300" "L222")
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
73
18383
11218164bc54 Add provide call.
Richard M. Stallman <rms@gnu.org>
parents: 15261
diff changeset
74 (provide 'soundex)
11218164bc54 Add provide call.
Richard M. Stallman <rms@gnu.org>
parents: 15261
diff changeset
75
5995
a24f3890171e Initial revision
Richard M. Stallman <rms@gnu.org>
parents:
diff changeset
76 ;; soundex.el ends here